Update README.md

README.md

@@ -21,5 +21,33 @@ pip install mlx-lm
 from mlx_lm import load, generate
 
 model, tokenizer = load("mlx-community/BiliBot-7B-Q")
-response = generate(model, tokenizer, prompt="hello", verbose=True)
+
+# Template content
+template = """
+<|im_start|>system
+You are a helpful assistant<|im_end|>
+<|im_start|>user
+请对以下问题给出简短、机智的回答：
+{usr_msg}<|im_end|>
+<|im_start|>assistant
+"""
+
+while True:
+    usr_msg = input("用户: ")  # Get user message from terminal
+    if usr_msg.lower() == 'quit()':  # Allows the user to exit the loop
+        break
+
+    prompt = template.replace("{usr_msg}", usr_msg)
+
+    time_ckpt = time.time()
+    response = generate(
+        model,
+        tokenizer,
+        prompt=prompt,
+        temp=0.3,
+        max_tokens=500,
+        verbose=False
+    )
+
+    print("%s: %s (Time %d ms)\n" % ("回答", response, (time.time() - time_ckpt) * 1000))
 ```